Braintrust vs Helicone: how to choose
Both log LLM calls, track cost and version prompts, and both offer a gateway. Helicone has been in maintenance mode since March 2026 and new cloud sign-ups are disabled; Braintrust is independent, raised an $80M Series B in February 2026 and is still adding evaluation features. For most teams the question is when to move off Helicone, not which to adopt.[1][6]
What is the difference between Braintrust and Helicone?
Braintrust is an active, hosted evaluation platform built around experiments and online scoring; Helicone is an open-source LLM request logger and AI gateway that has been in maintenance mode since March 2026, with new cloud sign-ups disabled. On 19 October 2026 Helicone said it is no longer part of Mintlify, with no new owner named. For a new deployment Braintrust is usually the practical choice; existing Helicone users should plan for the gateway and logging they rely on.
At a glance (checked 20 October 2026)
| Decision factor | Braintrust | Helicone |
|---|---|---|
| Ownership | Independent; $80M Series B in February 2026 | Acquired by Mintlify in March 2026; on 19 October 2026 said it is no longer part of Mintlify, no new owner named |
| Status | Active; several new features in public preview | Maintenance mode since March 2026; no feature changelog entries after November 2025 |
| Evaluation | Experiments, online scoring, LLM and code scorers, human review | Not an evaluation framework, by its own docs; Python evaluators turned off October 2026 |
| Gateway | Braintrust Gateway, public preview, free, no SLA | AI Gateway for 100+ providers with failover, caching and rate limits |
| Self-hosting | Enterprise only, data plane only; Braintrust runs the control plane | Apache-2.0; Docker, Compose or Helm |
| Agent tracing | One trace per run, including tool calls and handoffs | Header-based session grouping; no span model for agent steps |
| Free tier | Starter: 1 GB processed data, 10K scores, 14-day retention | Hobby: 10K requests, 7-day retention, existing accounts only |
| First paid tier | Pro: $249 a month | Pro: $79 a month, existing accounts only |
Braintrust vs Helicone: capabilities side by side
| Capability | Braintrust | Helicone | Prefactor |
|---|---|---|---|
| Observe | |||
| LLM call tracing | ✓ | ✓ | ✓ |
| Multi-step agent tracing (tool calls, nested spans) | ✓ | Partial | ✓ |
| Cost tracking | ✓ | ✓ | ✓ |
| OpenTelemetry support | ✓ | Partial | ✓ |
| Evaluate | |||
| Offline evals (datasets, experiments) | ✓ | Partial | ✓ |
| Online evals on production traffic | ✓ | Partial | ✓ |
| LLM-as-a-judge scoring | ✓ | Partial | ✓ |
| Code-based evaluators | ✓ | — | ✓ |
| Human review and annotation | ✓ | Partial | ✓ |
| Prompt versioning and playground | ✓ | ✓ | — |
| Act on findings | |||
| Runtime controls on live agent actions | — | Partial | ✓ |
| Gateway or proxy in the request path | ✓ | ✓ | — |
| Licence and deployment | |||
| Open source | Partial | ✓ | Partial |
| Self-hosting | Partial | ✓ | Partial |
Helicone is in maintenance mode
Mintlify acquired Helicone in March 2026 and moved it to a maintenance-only phase of patches, bug fixes and new model support, and cloud sign-ups have been disabled since 3 March 2026, so a new team cannot open an account. On 19 October 2026 the site began saying Helicone is no longer part of Mintlify, with details to come.
Read more
In May 2026 an AWS account lock took Helicone's dashboard and log processing down for about four days while the proxy stayed up. Braintrust is independent and shipping: Patterns, Topics, a thread view and workflow evals arrived in September and October 2026.
What each was built to do
Helicone is a proxy and AI Gateway in the request path, giving one OpenAI-compatible endpoint for more than 100 providers, and its documentation says it does not run evaluations. Braintrust is built around evaluation: datasets, tasks and scorers run as experiments, with the same scorers applied to sampled production logs.
Read more
Helicone adds failover, caching, rate limits and exact per-request cost for more than 300 models, but groups agent requests into sessions by header without a span model. Braintrust records each agent run as one trace with tool calls, handoffs and nested model calls and supports blind human review. Both alert on cost.
Moving from Helicone to Braintrust
Braintrust accepts OTLP and lists OpenTelemetry and Traceloop OpenLLMetry among its integrations, so Helicone's OpenLLMetry-based async logging can be repointed rather than rewritten. Teams on Helicone's proxy integration need Braintrust's SDK wrappers or framework integrations instead.
Read more
Plan the gateway separately: Braintrust's Gateway covers OpenAI, Anthropic, Google, AWS and others but is a preview with no SLA, and its earlier AI proxy is deprecated. Prompts move to Braintrust's prompt versioning. Helicone self-hosts fully under Apache-2.0, while Braintrust self-hosting is Enterprise only and covers the data plane, with Braintrust always operating the control plane, including the UI and authentication.
Pricing shape
As of 20 October 2026, Braintrust's Starter plan is free with 1 GB of processed data, 10K scores and 14-day retention, and Pro is $249 a month with 5 GB, 50K scores and 30-day retention, both with unlimited users. Helicone lists Hobby free with 10K requests, Pro at $79 a month and Team at $799 a month, for existing accounts only while sign-ups are disabled.
Read more
Braintrust charges $4 per extra GB on Starter and $3 on Pro, and $2.50 or $1.50 per 1,000 extra scores; Pro includes $100 a month in model credits. See Braintrust's pricing and Helicone's pricing.
Where Prefactor fits
We sell the layer this section describes. Read it with that in mind.
Stated plainly, since Prefactor publishes this page: Prefactor is an agent evaluation platform that scores each step of a run and acts on what it finds through runtime policies on tool calls and data access, approval holds for risky actions, and a kill switch for a run, an agent or a team. Braintrust scores after logging and does not block live actions; Helicone's gateway can block prompt injection for OpenAI models only. Neither holds a tool action for approval. Prefactor has no prompt playground or prompt registry, no gateway, and its platform is hosted, so it does not replace Helicone's routing or Braintrust's prompt iteration. See the full comparison of 15 platforms.
Which one fits
Pick Braintrust if
- You are starting a new deployment and need an evaluation platform that is shipping.
- Your work starts from datasets, experiments and scorers.
- Unlimited users on every plan suits how many people need access.
- A gateway in public preview is acceptable, or you use a separate one.
Stay on Helicone for now if
- You self-host it and it covers your logging while you plan a move.
- Production routing depends on its gateway and no replacement is chosen yet.
- You accept maintenance-only changes for the time being.
- You want to see Helicone's next owner before you migrate.
How we reviewed this comparison
Reviewed against public product and documentation pages on October 20, 2026. If a vendor has changed a feature, product name, or positioning since then, send a correction and we will update it. Numbered source links in the page body point to the ordered sources below.
Sources reviewed
- Braintrust pricingChecked 2026-10-20.
- Braintrust documentation
- Braintrust website
- Helicone pricingChecked 2026-10-20.
- Helicone documentation
- Helicone ownership and status
- Prefactor platform
Methodology
- Reviewed public product, documentation, and launch material visible at the time of writing.
- Mapped each page to the primary buyer, control layer, and runtime capabilities each vendor describes publicly.
- Prefer direct product and documentation pages over analyst summaries or reseller material.
What is the difference between Braintrust and Helicone?
How does Prefactor compare with Braintrust and Helicone?
Can I still sign up for Helicone?
Can Braintrust replace Helicone's gateway?
How do I move traces from Helicone to Braintrust?
What does maintenance mode mean for Helicone users?
Who owns Braintrust?
Is Braintrust open source?
How much does Braintrust cost?
Can Braintrust block or hold a live agent action?
Who owns Helicone?
Is Helicone open source?
How much does Helicone cost?
Can Helicone block or hold a live agent action?
Is Prefactor open source?
How much does Prefactor cost?
Can Prefactor block or hold a live agent action?
Score the run, then act on it
Prefactor scores each step of every agent run and can hold or stop an action when a score says it should not happen. Start on the free tier: 5,000 spans a month, no credit card required.
Unified performance platform for agents, authentication, and risk management